Python实现Word图片提取与批量处理的最佳实践

pip install Spire.Doc

from spire.doc import *
import os


def extract_images_from_single_doc(doc_path, output_folder):
    """
    从单个Word文档中提取图片并保存。
    :param doc_path: Word文档的完整路径。
    :param output_folder: 图片保存的目录。
    """
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)

    document = Document()
    document.LoadFromFile(doc_path)

    print(f"正在处理文档: {os.path.basename(doc_path)}")

    image_count = 0
    # 遍历文档的所有节
    for i in range(document.Sections.Count):
        section = document.Sections.get_Item(i)
        # 遍历节中的所有段落
        for j in range(section.Paragraphs.Count):
            paragraph = section.Paragraphs.get_Item(j)
            # 遍历段落中的所有子元素
            for k in range(paragraph.ChildObjects.Count):
                doc_object = paragraph.ChildObjects.get_Item(k)
                if doc_object.DocumentObjectType == DocumentObjectType.Picture:
                    picture = doc_object if isinstance(doc_object, DocPicture) else None
                    if picture is not None:
                        image_bytes = picture.ImageBytes
                        # 构建图片文件名，包含原始文档名和图片索引
                        image_name = f"{os.path.splitext(os.path.basename(doc_path))[0]}_image_{image_count}.png"
                        image_path = os.path.join(output_folder, image_name)
                        with open(image_path, "wb") as f:
                            f.write(image_bytes)
                        print(f"  - 提取图片: {image_name}")
                        image_count += 1

    document.Close()
    print(f"从 {os.path.basename(doc_path)} 中提取了 {image_count} 张图片。")

# 示例用法
# doc_file = "path/to/your/document.docx"
# output_dir = "extracted_images"
# extract_images_from_single_doc(doc_file, output_dir)

from spire.doc import *


def batch_extract_images_from_docs(input_folder, output_base_folder):
    """
    批量从指定文件夹下的所有Word文档中提取图片。
    :param input_folder: 包含Word文档的输入目录。
    :param output_base_folder: 所有提取图片保存的根目录，会为每个文档创建子文件夹。
    """
    if not os.path.exists(output_base_folder):
        os.makedirs(output_base_folder)

    for filename in os.listdir(input_folder):
        if filename.endswith(".docx") or filename.endswith(".doc"):
            doc_path = os.path.join(input_folder, filename)

            # 为每个文档创建一个独立的输出子文件夹
            doc_output_folder = os.path.join(output_base_folder, os.path.splitext(filename)[0])
            if not os.path.exists(doc_output_folder):
                os.makedirs(doc_output_folder)

            try:
                document = Document()
                document.LoadFromFile(doc_path)
                print(f"\n--- 正在处理文档: {filename} ---")

                image_count = 0
                for i in range(document.Sections.Count):
                    section = document.Sections.get_Item(i)
                    for j in range(section.Paragraphs.Count):
                        paragraph = section.Paragraphs.get_Item(j)
                        for k in range(paragraph.ChildObjects.Count):
                            doc_object = paragraph.ChildObjects.get_Item(k)
                            if doc_object.DocumentObjectType == DocumentObjectType.Picture:
                                picture = doc_object if isinstance(doc_object, DocPicture) else None
                                if picture is not None:
                                    image_bytes = picture.ImageBytes
                                    image_name = f"image_{image_count}.png"  # 命名图片，避免与不同文档的图片重名
                                    image_path = os.path.join(doc_output_folder, image_name)
                                    with open(image_path, "wb") as f:
                                        f.write(image_bytes)
                                    print(f"  - 提取图片: {image_name}")
                                    image_count += 1

                document.Close()
                print(f"从 {filename} 中提取了 {image_count} 张图片，保存至 {doc_output_folder}")

            except Exception as e:
                print(f"处理文档 {filename} 时发生错误: {e}")
        else:
            print(f"跳过非Word文档: {filename}")


# 示例用法
input_directory = "path/to/your/word_documents"  # 存放所有Word文档的目录
output_directory = "batch_extracted_images"  # 图片提取后的总输出目录
# batch_extract_images_from_docs(input_directory, output_directory)

import hashlib

# ... (接上述批量处理代码)

# 在保存图片的代码块内，可以加入哈希去重逻辑
# ...
                                if picture is not None:
                                    image_bytes = picture.ImageBytes
                                    # 计算图片内容的MD5哈希值
                                    image_hash = hashlib.md5(image_bytes).hexdigest()
                                    
                                    # 检查是否已存在相同哈希值的图片
                                    # 这里需要一个全局或文档级别的set来存储已保存的哈希值
                                    # For simplicity, let's assume we save all for now, 
                                    # but in a real scenario, you'd check a set of hashes.
                                    
                                    image_name = f"{image_hash}.png" # 使用哈希值作为文件名，方便去重
                                    image_path = os.path.join(doc_output_folder, image_name)
                                    
                                    if not os.path.exists(image_path): # 只有当图片文件不存在时才写入
                                        with open(image_path, "wb") as f:
                                            f.write(image_bytes)
                                        print(f"  - 提取并保存新图片: {image_name}")
                                    else:
                                        print(f"  - 发现重复图片，已跳过: {image_name}")
                                    image_count += 1
# ...